Learned lessons in credit card fraud detection from ... - Semantic Scholar
Accepted Manuscript Learned lessons in credit card fraud detection from a practitioner perspective Andrea DAL POZZOLO, Olivier CAELEN, Yann-Aël LE BORGNE, Serge WATERSCHOOT, Gianluca BONTEMPI PII: DOI: Reference:
S0957-4174(14)00089-X http://dx.doi.org/10.1016/j.eswa.2014.02.026 ESWA 9186
To appear in:
Expert Systems with Applications
Please cite this article as: POZZOLO, A.D., CAELEN, O., BORGNE, Y.L., WATERSCHOOT, S., BONTEMPI, G., Learned lessons in credit card fraud detection from a practitioner perspective, Expert Systems with Applications (2014), doi: http://dx.doi.org/10.1016/j.eswa.2014.02.026
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Learned lessons in credit card fraud detection from a practitioner perspective Andrea DAL POZZOLOa , Olivier CAELENb , Yann-A¨el LE BORGNEa , Serge WATERSCHOOTb , Gianluca BONTEMPIa a
Machine Learning Group, Computer Science Department, Faculty of Sciences ULB, Universit´e Libre de Bruxelles, Brussels, Belgium b Fraud Risk Management Analytics, Worldline, Brussels, Belgium
Abstract Billions of dollars of loss are caused every year due to fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to non stationary distribution of the data, highly imbalanced classes distributions and continuous streams of transactions. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about which is the best strategy to deal with them. In this paper we provide some answers from the practitioner’s perspective by focusing on three crucial issues: unbalancedness, non-stationarity and assessment. The analysis is made possible by a real credit card dataset provided by our industrial partner. Keywords: Incremental Learning, Unbalanced data, Fraud detection
Email addresses: [email protected] (Andrea DAL POZZOLO), [email protected] (Olivier CAELEN), [email protected] (Yann-A¨el LE BORGNE), [email protected] (Serge WATERSCHOOT), [email protected] (Gianluca BONTEMPI)
Preprint submitted to Expert Systems with Applications
February 18, 2014
S0957-4174(14)00089-X http://dx.doi.org/10.1016/j.eswa.2014.02.026 ESWA 9186
To appear in:
Expert Systems with Applications
Please cite this article as: POZZOLO, A.D., CAELEN, O., BORGNE, Y.L., WATERSCHOOT, S., BONTEMPI, G., Learned lessons in credit card fraud detection from a practitioner perspective, Expert Systems with Applications (2014), doi: http://dx.doi.org/10.1016/j.eswa.2014.02.026
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.
Learned lessons in credit card fraud detection from a practitioner perspective Andrea DAL POZZOLOa , Olivier CAELENb , Yann-A¨el LE BORGNEa , Serge WATERSCHOOTb , Gianluca BONTEMPIa a
Machine Learning Group, Computer Science Department, Faculty of Sciences ULB, Universit´e Libre de Bruxelles, Brussels, Belgium b Fraud Risk Management Analytics, Worldline, Brussels, Belgium
Abstract Billions of dollars of loss are caused every year due to fraudulent credit card transactions. The design of efficient fraud detection algorithms is key for reducing these losses, and more and more algorithms rely on advanced machine learning techniques to assist fraud investigators. The design of fraud detection algorithms is however particularly challenging due to non stationary distribution of the data, highly imbalanced classes distributions and continuous streams of transactions. At the same time public data are scarcely available for confidentiality issues, leaving unanswered many questions about which is the best strategy to deal with them. In this paper we provide some answers from the practitioner’s perspective by focusing on three crucial issues: unbalancedness, non-stationarity and assessment. The analysis is made possible by a real credit card dataset provided by our industrial partner. Keywords: Incremental Learning, Unbalanced data, Fraud detection
Email addresses: [email protected] (Andrea DAL POZZOLO), [email protected] (Olivier CAELEN), [email protected] (Yann-A¨el LE BORGNE), [email protected] (Serge WATERSCHOOT), [email protected] (Gianluca BONTEMPI)
Preprint submitted to Expert Systems with Applications
February 18, 2014
